# 4bit Quantized Inference

Llama model trained with Unsloth and Huggingface TRL library, achieving 2x faster inference speed

A multimodal large language model fine-tuned based on unsloth/llama-3.2-11b-vision-instruct-unsloth-bnb-4bit, supporting visual instruction understanding tasks, with Unsloth optimization doubling training speed.

BNB-NF4 quantized version of AWPortrait-FL, a text-to-image generation model developed based on FLUX.1-dev

This model is a 4bit quantized version converted from CohereForAI/c4ai-command-r-v01 to MLX format, supporting multilingual conversations and tool usage.